Switchable metasurfaces from phase change materials designed with machine learning

Chalcogenide phase change materials (PCMs) are uniquely suited for spectral tuning applications due to their contrasting dielectric material properties. Recent headway has been made towards realizing tunable photonic devices using twodimensional, sub-wavelength resonators by carefully designing geometries that optimize optical, electrical, and thermal performances using multi-physics analyses and machine learning. In this paper, we tackle two other essential aspects for creating application-specific, tunable PCM devices: (1) scalability of the device size and (2) high-throughput fabrication techniques. We employ a deep ultraviolet (DUV) stepper projection lithography to manufacture over 100 densely packed GST metasurfaces, each with a sample size of 5×7 mm², all on a 4-inch Al₂O₃ wafer. These metasurface structures were discovered using artificial neural network (ANN) techniques and confirmed by finite-difference-time domain calculations. The primary structures under investigation were nanobar configurations enabling amplitude modulation at short-wave infrared wavelengths to realize efficient optical switches for free space optical multiplexing. The DUV fabrication technique can easily be extended to other metasurface geometries to demonstrate multi-functional, non-volatile photonic devices.